FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations
This addresses alert fatigue for fraud analysts in e-commerce companies, though it appears incremental as it applies existing LLM capabilities to a specific domain.
The paper tackles the problem of overwhelming fraud analysts with numerous credit card transaction alerts by proposing a fraud analyst assistant (FAA) framework that uses multi-modal large language models to automate investigations and generate reports, demonstrating through an evaluation of 500 cases that it produces reliable and efficient investigations with an average of seven steps.
The continuous growth of the e-commerce industry attracts fraudsters who exploit stolen credit card details. Companies often investigate suspicious transactions in order to retain customer trust and address gaps in their fraud detection systems. However, analysts are overwhelmed with an enormous number of alerts from credit card transaction monitoring systems. Each alert investigation requires from the fraud analysts careful attention, specialized knowledge, and precise documentation of the outcomes, leading to alert fatigue. To address this, we propose a fraud analyst assistant (FAA) framework, which employs multi-modal large language models (LLMs) to automate credit card fraud investigations and generate explanatory reports. The FAA framework leverages the reasoning, code execution, and vision capabilities of LLMs to conduct planning, evidence collection, and analysis in each investigation step. A comprehensive empirical evaluation of 500 credit card fraud investigations demonstrates that the FAA framework produces reliable and efficient investigations comprising seven steps on average. Thus we found that the FAA framework can automate large parts of the workload and help reduce the challenges faced by fraud analysts.